Speed estimation plays an important role in many components in intelligent transportation systems (ITS). In practice, traffic data from single loop detectors are one of the dominant data sources. Speed estimation from single loop detectors is mainly based on occupancy data, a conversion factor from occupancy to density (which is potentially related to the vehicle length), and the assumed relationship between flow, speed, and density. This paper investigates the discrepancy between the speed estimated with single loops and the speed estimated with double loops. It was found that the discrepancy between the two is mainly caused by the high variance in vehicle pace, which, especially under congested traffic, is often accompanied with the high skewness. Accuracy can be improved by computing occupancy in a different way, using the median vehicle passage time over the detector as opposed to the mean vehicle passage time often used in the conventional method. The performance of the enhanced speed estimation method is very promising. The use of the median vehicle passage time reduces the skewness of pace data.